{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T16:36:27Z","timestamp":1754152587324,"version":"3.41.2"},"reference-count":155,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"New Energy and Industrial Technology Development Organization","award":["JPNP23003"],"award-info":[{"award-number":["JPNP23003"]}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"crossref","award":["ALCA-Next JPMJAN24B1"],"award-info":[{"award-number":["ALCA-Next JPMJAN24B1"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Reservoir computing (RC) systems, traditionally based on echo state networks (ESN) or liquid state machines, have shown significant potential in dynamic temporal data modeling, such as weather forecasting and astronomical predictions. However, these frameworks are known not being applicable to quantum dynamics-based RC. Tensor networks (TNs), with their efficient representation of high-dimensional quantum information and entanglement, are powerful tools for modeling correlated quantum dynamics. Introducing randomized effects into TNs, akin to randomization of recurrent connections in traditional RC, is expected to generate diverse quantum correlation patterns and provide robust, generalizable quantum-inspired dynamic models through randomization. In this work, we propose a novel randomized TN-based RC scheme, experimentally demonstrating its validity. A theoretical model selection criterion is constructed to find the optimal TNRC hyperparameters. Critical phenomena along with the phase transitions of learnability near the edge of chaos in TN RC are clearly identified. The distribution-independent universality in phase transitions observed in TN RC is captured by the newly developed learning theory and a self-consistent mean-field theory of the spin-glass type. The performance advantage of TNRC over ESN is demonstrated in several forecasting experiments. Our findings lay the groundwork for future explorations into randomized TN quantum machine learning, phase transitions in quantum RC, and the manipulation of critical phenomena in complex systems.<\/jats:p>","DOI":"10.1088\/2632-2153\/aded56","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T09:24:23Z","timestamp":1752139463000},"page":"035011","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Randomized tensor network reservoir computing: validity and learnability phase transitions"],"prefix":"10.1088","volume":"6","author":[{"given":"Shinji","family":"Sato","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9601-0773","authenticated-orcid":true,"given":"Daiki","family":"Sasaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3092-4346","authenticated-orcid":true,"given":"Chih-Chieh","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kodai","family":"Shiba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9258-6130","authenticated-orcid":true,"given":"Tomah","family":"Sogabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,7,22]]},"reference":[{"year":"2001","author":"Jaeger","doi-asserted-by":"publisher","key":"mlstaded56bib1","DOI":"10.24406\/publica-fhg-291111"},{"key":"mlstaded56bib2","doi-asserted-by":"publisher","first-page":"2531","DOI":"10.1162\/089976602760407955","article-title":"Real-time computing without stable states: a new framework for neural computation based on perturbations","volume":"14","author":"Maass","year":"2002","journal-title":"Neural Comput."},{"key":"mlstaded56bib3","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1126\/science.1091277","article-title":"Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication","volume":"304","author":"Jaeger","year":"2004","journal-title":"Science"},{"key":"mlstaded56bib4","doi-asserted-by":"publisher","DOI":"10.35848\/1347-4065\/ab8d4f","article-title":"Physical reservoir computing\u2014an introductory perspective","volume":"59","author":"Nakajima","year":"2020","journal-title":"Jpn. J. Appl. Phys."},{"year":"1962","author":"Rosenblatt","key":"mlstaded56bib5"},{"key":"mlstaded56bib6","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.1109\/T-C.1972.223477","article-title":"Learning patterns and pattern sequences by self-organizing nets of threshold elements","volume":"C\u201321","author":"Amari","year":"1972","journal-title":"IEEE Trans. Comput."},{"key":"mlstaded56bib7","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1109\/IJCNN.2004.1380068","article-title":"Extreme learning machine: a new learning scheme of feedforward neural networks","volume":"vol 2","author":"Huang","year":"2004"},{"key":"mlstaded56bib8","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.cosrev.2009.03.005","article-title":"Reservoir computing approaches to recurrent neural network training","volume":"3","author":"Luko\u0161evi\u010dius","year":"2009","journal-title":"Comput. Sci. Rev."},{"key":"mlstaded56bib9","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.neunet.2019.03.005","article-title":"Recent advances in physical reservoir computing: a review","volume":"115","author":"Tanaka","year":"2019","journal-title":"Neural Netw."},{"key":"mlstaded56bib10","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1109\/TCS.1985.1085649","article-title":"Fading memory and the problem of approximating nonlinear operators with Volterra series","volume":"32","author":"Boyd","year":"1985","journal-title":"IEEE Trans. Circuits Syst."},{"key":"mlstaded56bib11","doi-asserted-by":"publisher","first-page":"5564","DOI":"10.1038\/s41467-021-25801-2","article-title":"Next generation reservoir computing","volume":"12","author":"Gauthier","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstaded56bib12","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/ac7db7","article-title":"Hands-on reservoir computing: a tutorial for practical implementation","volume":"2","author":"Cucchi","year":"2022","journal-title":"Neuromorph. Comput. Eng."},{"key":"mlstaded56bib13","doi-asserted-by":"publisher","first-page":"2056","DOI":"10.1038\/s41467-024-45187-1","article-title":"Emerging opportunities and challenges for the future of reservoir computing","volume":"15","author":"Yan","year":"2024","journal-title":"Nat. Commun."},{"key":"mlstaded56bib14","doi-asserted-by":"publisher","first-page":"eade1156","DOI":"10.1126\/sciadv.ade1156","article-title":"Edge-of-chaos learning achieved by ion-electron\u2013coupled dynamics in an ion-gating reservoir","volume":"8","author":"Nishioka","year":"2022","journal-title":"Sci. Adv."},{"key":"mlstaded56bib15","doi-asserted-by":"publisher","DOI":"10.1038\/srep10487","article-title":"Information processing via physical soft body","volume":"5","author":"Nakajima","year":"2015","journal-title":"Sci. Rep."},{"key":"mlstaded56bib16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.14.024065","article-title":"Temporal information processing on noisy quantum computers","volume":"14","author":"Chen","year":"2020","journal-title":"Phys. Rev. Appl."},{"key":"mlstaded56bib17","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1038\/s41598-022-05061-w","article-title":"Natural quantum reservoir computing for temporal information processing","volume":"12","author":"Suzuki","year":"2022","journal-title":"Sci. Rep."},{"key":"mlstaded56bib18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.108.042609","article-title":"Impact of the form of weighted networks on the quantum extreme reservoir computation","volume":"108","author":"Hayashi","year":"2023","journal-title":"Phys. Rev. A"},{"key":"mlstaded56bib19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.8.024030","article-title":"Harnessing disordered-ensemble quantum dynamics for machine learning","volume":"8","author":"Fujii","year":"2017","journal-title":"Phys. Rev. Appl."},{"key":"mlstaded56bib20","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ad133e","article-title":"Quantum-classical hybrid neural networks in the neural tangent kernel regime","volume":"9","author":"Nakaji","year":"2023","journal-title":"Quantum Sci. Technol."},{"key":"mlstaded56bib21","doi-asserted-by":"publisher","first-page":"4008","DOI":"10.1038\/s41467-021-24260-z","article-title":"Avalanches and edge-of-chaos learning in neuromorphic nanowire networks","volume":"12","author":"Hochstetter","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstaded56bib22","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1038\/srep00287","article-title":"Optoelectronic reservoir computing","volume":"2","author":"Paquot","year":"2012","journal-title":"Sci. Rep."},{"key":"mlstaded56bib23","doi-asserted-by":"publisher","first-page":"3541","DOI":"10.1038\/ncomms4541","article-title":"Experimental demonstration of reservoir computing on a silicon photonics chip","volume":"5","author":"Vandoorne","year":"2014","journal-title":"Nat. Commun."},{"key":"mlstaded56bib24","doi-asserted-by":"publisher","first-page":"31356","DOI":"10.1364\/OE.22.031356","article-title":"Integrated photonic reservoir computing based on hierarchical time-multiplexing structure","volume":"22","author":"Zhang","year":"2014","journal-title":"Opt. Express"},{"key":"mlstaded56bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.10.034063","article-title":"Macromagnetic simulation for reservoir computing utilizing spin dynamics in magnetic tunnel junctions","volume":"10","author":"Furuta","year":"2018","journal-title":"Phys. Rev. Appl."},{"key":"mlstaded56bib26","doi-asserted-by":"publisher","DOI":"10.1063\/1.5081797","article-title":"Physical reservoir computing based on spin torque oscillator with forced synchronization","volume":"114","author":"Tsunegi","year":"2019","journal-title":"Appl. Phys. Lett."},{"key":"mlstaded56bib27","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.11.034021","article-title":"Boosting computational power through spatial multiplexing in quantum reservoir computing","volume":"11","author":"Nakajima","year":"2019","journal-title":"Phys. Rev. Appl."},{"key":"mlstaded56bib28","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.127.100502","article-title":"Dynamical phase transitions in quantum reservoir computing","volume":"127","author":"Mart\u00ednez-Pe\u00f1a","year":"2021","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib29","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/BF01217347","article-title":"Computation theory of cellular automata","volume":"96","author":"Wolfram","year":"1984","journal-title":"Commun. Math. Phys."},{"key":"mlstaded56bib30","first-page":"435","article-title":"Machine learning using cellular automata based feature expansion and reservoir computing","volume":"10","author":"Y\u0131lmaz","year":"2015","journal-title":"J. Cell Autom."},{"key":"mlstaded56bib31","doi-asserted-by":"publisher","DOI":"10.1063\/1.5097686","article-title":"Network structure effects in reservoir computers","volume":"29","author":"Carroll","year":"2019","journal-title":"Chaos Interdiscip. J. Nonlinear Sci."},{"key":"mlstaded56bib32","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/TNN.2010.2089641","article-title":"Minimum complexity echo state network","volume":"22","author":"Rodan","year":"2011","journal-title":"IEEE Trans. Neural Netw."},{"key":"mlstaded56bib33","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.131.036502","article-title":"Can neural quantum states learn volume-law ground states?","volume":"131","author":"Passetti","year":"2023","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib34","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.91.045002","article-title":"Machine learning and the physical sciences","volume":"91","author":"Carleo","year":"2019","journal-title":"Rev. Mod. Phys."},{"key":"mlstaded56bib35","doi-asserted-by":"publisher","DOI":"10.1088\/2399-6528\/ac7d39","article-title":"Quantum circuit architectures via quantum observable Markov decision process planning","volume":"6","author":"Kimura","year":"2022","journal-title":"J. Phys. Commun."},{"key":"mlstaded56bib36","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-52275-6","article-title":"Hybrid classical-quantum linear solver using Noisy Intermediate-Scale Quantum machines","volume":"9","author":"Chen","year":"2019","journal-title":"Sci. Rep."},{"key":"mlstaded56bib37","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1038\/s42254-019-0086-7","article-title":"Tensor networks for complex quantum systems","volume":"1","author":"Or\u00fas","year":"2019","journal-title":"Nat. Rev. Phys."},{"key":"mlstaded56bib38","doi-asserted-by":"publisher","first-page":"2863","DOI":"10.1103\/PhysRevLett.69.2863","article-title":"Density matrix formulation for quantum renormalization groups","volume":"69","author":"White","year":"1992","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib39","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1143\/JPSJ.65.891","article-title":"Corner transfer matrix renormalization group method","volume":"65","author":"Nishino","year":"1996","journal-title":"J. Phys. Soc. Japan"},{"key":"mlstaded56bib40","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.96.220601","article-title":"Criticality, the area law, and the computational power of projected entangled pair states","volume":"96","author":"Verstraete","year":"2006","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib41","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.99.220405","article-title":"Entanglement renormalization","volume":"99","author":"Vidal","year":"2007","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib42","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.124.037201","article-title":"Isometric tensor network states in two dimensions","volume":"124","author":"Zaletel","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib43","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.66.045114","article-title":"Dynamical density-matrix renormalization-group method","volume":"66","author":"Jeckelmann","year":"2002","journal-title":"Phys. Rev. B"},{"key":"mlstaded56bib44","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","article-title":"Tensor-train decomposition","volume":"33","author":"Oseledets","year":"2011","journal-title":"SIAM J. Sci. Comput."},{"key":"mlstaded56bib45","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1103\/RevModPhys.82.277","article-title":"Colloquium: area laws for the entanglement entropy","volume":"82","author":"Eisert","year":"2010","journal-title":"Rev. Mod. Phys."},{"key":"mlstaded56bib46","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.100.030504","article-title":"Entropy scaling and simulability by matrix product states","volume":"100","author":"Schuch","year":"2008","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib47","doi-asserted-by":"publisher","first-page":"3537","DOI":"10.1103\/PhysRevLett.75.3537","article-title":"Thermodynamic limit of density matrix renormalization","volume":"75","author":"\u00d6stlund","year":"1995","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib48","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.aop.2010.09.012","article-title":"The density-matrix renormalization group in the age of matrix product states","volume":"326","author":"Schollw\u00f6ck","year":"2011","journal-title":"Ann. Phys."},{"key":"mlstaded56bib49","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1209\/epl\/i1998-00381-x","article-title":"Equivalence of the variational matrix product method and the density matrix renormalization group applied to spin chains","volume":"43","author":"Dukelsky","year":"1998","journal-title":"Europhys. Lett."},{"key":"mlstaded56bib50","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.91.147902","article-title":"Efficient classical simulation of slightly entangled quantum computations","volume":"91","author":"Vidal","year":"2003","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib51","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.77.144302","article-title":"Observations outside the light cone: algorithms for nonequilibrium and thermal states","volume":"77","author":"Hastings","year":"2008","journal-title":"Phys. Rev. B"},{"key":"mlstaded56bib52","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.4.020304","article-title":"Density-matrix renormalization group algorithm for simulating quantum circuits with a finite fidelity","volume":"4","author":"Ayral","year":"2023","journal-title":"PRX Quantum"},{"key":"mlstaded56bib53","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.101.032310","article-title":"Encoding of matrix product states into quantum circuits of one- and two-qubit gates","volume":"101","author":"Ran","year":"2020","journal-title":"Phys. Rev. A"},{"key":"mlstaded56bib54","article-title":"Supervised learning with tensor networks","volume":"vol 29","author":"Stoudenmire","year":"2016"},{"year":"2019","author":"Efthymiou","article-title":"TensorNetwork for machine learning","key":"mlstaded56bib55"},{"key":"mlstaded56bib56","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.031012","article-title":"Unsupervised generative modeling using matrix product states","volume":"8","author":"Han","year":"2018","journal-title":"Phys. Rev. X"},{"key":"mlstaded56bib57","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac44a9","article-title":"Mutual information scaling for tensor network machine learning","volume":"3","author":"Convy","year":"2022","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstaded56bib58","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1162\/neco_a_01202","article-title":"Matrix product state\u2013based quantum classifier","volume":"31","author":"Bhatia","year":"2019","journal-title":"Neural Comput."},{"key":"mlstaded56bib59","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.103.125117","article-title":"Supervised learning with projected entangled pair states","volume":"103","author":"Cheng","year":"2021","journal-title":"Phys. Rev. B"},{"key":"mlstaded56bib60","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.4.043111","article-title":"Tensor network to learn the wave function of data","volume":"4","author":"Dymarsky","year":"2022","journal-title":"Phys. Rev. Res."},{"key":"mlstaded56bib61","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac104d","article-title":"An end-to-end trainable hybrid classical-quantum classifier","volume":"2","author":"Chen","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstaded56bib62","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/MSP.2013.2297439","article-title":"Tensor decompositions for signal processing applications: from two-way to multiway component analysis","volume":"32","author":"Cichocki","year":"2015","journal-title":"IEEE Signal Process. Mag."},{"key":"mlstaded56bib63","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/aaea94","article-title":"Towards quantum machine learning with tensor networks","volume":"4","author":"Huggins","year":"2019","journal-title":"Quantum Sci. Technol."},{"key":"mlstaded56bib64","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/ab31ef","article-title":"Machine learning by unitary tensor network of hierarchical tree structure","volume":"21","author":"Liu","year":"2019","journal-title":"New J. Phys."},{"key":"mlstaded56bib65","doi-asserted-by":"publisher","first-page":"142","DOI":"10.21468\/SciPostPhys.14.6.142","article-title":"Residual matrix product state for machine learning","volume":"14","author":"Meng","year":"2023","journal-title":"SciPost Phys."},{"key":"mlstaded56bib66","doi-asserted-by":"publisher","first-page":"0061","DOI":"10.34133\/icomputing.0061","article-title":"Tensor networks for interpretable and efficient quantum-inspired machine learning","volume":"2","author":"Ran","year":"2023","journal-title":"Intell. Comput."},{"key":"mlstaded56bib67","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2023.0218","article-title":"Tensor networks for quantum machine learning","volume":"479","author":"Rieser","year":"2023","journal-title":"Proc. R. Soc. A"},{"key":"mlstaded56bib68","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.1038\/s41567-023-02076-6","article-title":"Measurement-induced entanglement phase transition on a superconducting quantum processor with mid-circuit readout","volume":"19","author":"Koh","year":"2023","journal-title":"Nat. Phys."},{"key":"mlstaded56bib69","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.109.235102","article-title":"Random insights into the complexity of two-dimensional tensor network calculations","volume":"109","author":"Gonz\u00e1lez-Garc\u00eda","year":"2024","journal-title":"Phys. Rev. B"},{"key":"mlstaded56bib70","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1038\/s43588-021-00181-1","article-title":"A quantum-inspired approach to exploit turbulence structures","volume":"2","author":"Gourianov","year":"2022","journal-title":"Nat. Comput. Sci."},{"key":"mlstaded56bib71","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.129.200602","article-title":"Transitions in the learnability of global charges from local measurements","volume":"129","author":"Barratt","year":"2022","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib72","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.2.040308","article-title":"Emergent statistical mechanics from properties of disordered random matrix product states","volume":"2","author":"Haferkamp","year":"2021","journal-title":"PRX Quantum"},{"key":"mlstaded56bib73","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42005-019-0152-6","article-title":"Complex networks from classical to quantum","volume":"2","author":"Biamonte","year":"2019","journal-title":"Commun. Phys."},{"key":"mlstaded56bib74","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.97.033310","article-title":"Tensor renormalization group with randomized singular value decomposition","volume":"97","author":"Morita","year":"2018","journal-title":"Phys. Rev. E"},{"key":"mlstaded56bib75","doi-asserted-by":"publisher","DOI":"10.1063\/1.4936880","article-title":"Random matrix techniques in quantum information theory","volume":"57","author":"Collins","year":"2015","journal-title":"J. Math. Phys."},{"key":"mlstaded56bib76","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/s00220-013-1718-x","article-title":"Matrix product states, random matrix theory and the principle of maximum entropy","volume":"320","author":"Collins","year":"2013","journal-title":"Commun. Math. Phys."},{"key":"mlstaded56bib77","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.81.032336","article-title":"Typicality in random matrix product states","volume":"81","author":"Garnerone","year":"2010","journal-title":"Phys. Rev. A"},{"key":"mlstaded56bib78","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.97.110403","article-title":"Quantum phase transitions in matrix product systems","volume":"97","author":"Wolf","year":"2006","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib79","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1038\/srep00514","article-title":"Information processing capacity of dynamical systems","volume":"2","author":"Dambre","year":"2012","journal-title":"Sci. Rep."},{"year":"1988","author":"Packard","key":"mlstaded56bib80"},{"key":"mlstaded56bib81","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/0167-2789(90)90064-V","article-title":"Computation at the edge of chaos: phase transitions and emergent computation","volume":"42","author":"Langton","year":"1990","journal-title":"Phys. Nonlinear Phenom."},{"key":"mlstaded56bib82","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.neucom.2016.12.089","article-title":"Deep reservoir computing: a critical experimental analysis","volume":"268","author":"Gallicchio","year":"2017","journal-title":"Neurocomputing"},{"key":"mlstaded56bib83","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.3.043135","article-title":"Unifying framework for information processing in stochastically driven dynamical systems","volume":"3","author":"Kubota","year":"2021","journal-title":"Phys. Rev. Res."},{"key":"mlstaded56bib84","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1038\/s42256-021-00376-1","article-title":"Learning function from structure in neuromorphic networks","volume":"3","author":"Su\u00e1rez","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"mlstaded56bib85","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.82.174411","article-title":"Many-body localization phase transition","volume":"82","author":"Pal","year":"2010","journal-title":"Phys. Rev. B"},{"key":"mlstaded56bib86","doi-asserted-by":"publisher","DOI":"10.1007\/s11467-022-1158-1","article-title":"The reservoir learning power across quantum many-body localization transition","volume":"17","author":"Xia","year":"2022","journal-title":"Front. Phys."},{"key":"mlstaded56bib87","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1137\/1116025","article-title":"On the uniform convergence of relative frequencies of events to their probabilities","volume":"16","author":"Vapnik","year":"1971","journal-title":"Theory Probab. Appl."},{"key":"mlstaded56bib88","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1109\/34.55105","article-title":"A theory of the learnable","volume":"27","author":"Valiant","year":"1984","journal-title":"Commun. ACM"},{"key":"mlstaded56bib89","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1145\/76359.76371","article-title":"Learnability and the Vapnik-Chervonenkis dimension","volume":"36","author":"Blumer","year":"1989","journal-title":"J. ACM"},{"key":"mlstaded56bib90","first-page":"10931","article-title":"Lower and upper bounds on the pseudo-dimension of tensor network models","volume":"vol 34","author":"Khavari","year":"2021"},{"key":"mlstaded56bib91","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1038\/s43588-021-00084-1","article-title":"The power of quantum neural networks","volume":"1","author":"Abbas","year":"2021","journal-title":"Nat. Comput. Sci."},{"key":"mlstaded56bib92","doi-asserted-by":"publisher","first-page":"8:1","DOI":"10.1145\/3466797","article-title":"On the expressibility and overfitting of quantum circuit learning","volume":"2","author":"Chen","year":"2021","journal-title":"ACM Trans. Quantum Comput."},{"key":"mlstaded56bib93","doi-asserted-by":"publisher","first-page":"582","DOI":"10.22331\/q-2021-11-17-582","article-title":"Encoding-dependent generalization bounds for parametrized quantum circuits","volume":"5","author":"Caro","year":"2021","journal-title":"Quantum"},{"key":"mlstaded56bib94","doi-asserted-by":"publisher","DOI":"10.1088\/2632-072X\/ac9f9b","article-title":"General Vapnik\u2013Chervonenkis dimension bounds for quantum circuit learning","volume":"3","author":"Chen","year":"2022","journal-title":"J. Phys. Complex"},{"key":"mlstaded56bib95","doi-asserted-by":"publisher","first-page":"4919","DOI":"10.1038\/s41467-022-32550-3","article-title":"Generalization in quantum machine learning from few training data","volume":"13","author":"Caro","year":"2022","journal-title":"Nat. Commun."},{"key":"mlstaded56bib96","first-page":"1","article-title":"Risk bounds for reservoir computing","volume":"21","author":"Gonon","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"mlstaded56bib97","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s13662-022-03686-9","article-title":"Path classification by stochastic linear recurrent neural networks","volume":"2022","author":"Boutaib","year":"2022","journal-title":"Adv. Contin. Discrete Models"},{"key":"mlstaded56bib98","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1109\/ICC45855.2022.9839095","article-title":"Error bound characterization for reservoir computing-based OFDM symbol detection","author":"Jere","year":"2022"},{"key":"mlstaded56bib99","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106883","article-title":"Complexities of feature-based learning systems, with application to reservoir computing","volume":"182","author":"Yasumoto","year":"2025","journal-title":"Neural Netw."},{"key":"mlstaded56bib100","first-page":"868","article-title":"Analyzing finite neural networks: can we trust neural tangent kernel theory?","author":"Seleznova","year":"2022"},{"key":"mlstaded56bib101","first-page":"1032","article-title":"Universal Statistics of fisher information in deep neural networks: mean field approach","author":"Karakida","year":"2019"},{"key":"mlstaded56bib102","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.100.062312","article-title":"Optimal short-term memory before the edge of chaos in driven random recurrent networks","volume":"100","author":"Haruna","year":"2019","journal-title":"Phys. Rev. E"},{"key":"mlstaded56bib103","first-page":"8580","article-title":"Neural tangent kernel: convergence and generalization in neural networks","author":"Jacot","year":"2018"},{"key":"mlstaded56bib104","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.041029","article-title":"Optimal sequence memory in driven random networks","volume":"8","author":"Schuecker","year":"2018","journal-title":"Phys. Rev. X"},{"key":"mlstaded56bib105","article-title":"Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice","volume":"vol 30","author":"Pennington","year":"2017"},{"key":"mlstaded56bib106","article-title":"Exponential expressivity in deep neural networks through transient chaos","volume":"vol 29","author":"Poole","year":"2016"},{"year":"2016","author":"Schoenholz","article-title":"Deep information propagation","key":"mlstaded56bib107"},{"key":"mlstaded56bib108","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.87.042809","article-title":"Mean-field theory of echo state networks","volume":"87","author":"Massar","year":"2013","journal-title":"Phys. Rev. E"},{"year":"1996","author":"Neal","key":"mlstaded56bib109"},{"key":"mlstaded56bib110","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1088\/0305-4470\/21\/1\/031","article-title":"Optimal storage properties of neural network models","volume":"21","author":"Gardner","year":"1988","journal-title":"J. Phys.: Math. Gen."},{"key":"mlstaded56bib111","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/0893-6080(88)90022-6","article-title":"Statistical neurodynamics of associative memory","volume":"1","author":"Amari","year":"1988","journal-title":"Neural Netw."},{"year":"1987","author":"Mezard","key":"mlstaded56bib112"},{"key":"mlstaded56bib113","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1103\/PhysRevLett.61.259","article-title":"Chaos in random neural networks","volume":"61","author":"Sompolinsky","year":"1988","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib114","doi-asserted-by":"publisher","first-page":"1530","DOI":"10.1103\/PhysRevLett.55.1530","article-title":"Storing infinite numbers of patterns in a spin-glass model of neural networks","volume":"55","author":"Amit","year":"1985","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib115","doi-asserted-by":"publisher","first-page":"2554","DOI":"10.1073\/pnas.79.8.2554","article-title":"Neural networks and physical systems with emergent collective computational abilities","volume":"79","author":"Hopfield","year":"1982","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstaded56bib116","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1080\/14786437708235992","article-title":"Solution of \u2018Solvable model of a spin glass\u2019","volume":"35","author":"Thouless","year":"1977","journal-title":"Phil. Mag. J. Theor. Exp. Appl. Phys."},{"key":"mlstaded56bib117","doi-asserted-by":"publisher","first-page":"4384","DOI":"10.1103\/PhysRevB.17.4384","article-title":"Infinite-ranged models of spin-glasses","volume":"17","author":"Kirkpatrick","year":"1978","journal-title":"Phys. Rev. B"},{"key":"mlstaded56bib118","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1088\/0305-4608\/5\/5\/017","article-title":"Theory of spin glasses","volume":"5","author":"Edwards","year":"1975","journal-title":"J. Phys. F: Met. Phys."},{"key":"mlstaded56bib119","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.128.168301","article-title":"Gell-mann\u2013low criticality in neural networks","volume":"128","author":"Tiberi","year":"2022","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib120","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.97.053304","article-title":"Scale-invariant feature extraction of neural network and renormalization group flow","volume":"97","author":"Iso","year":"2018","journal-title":"Phys. Rev. E"},{"key":"mlstaded56bib121","doi-asserted-by":"publisher","first-page":"4840","DOI":"10.1038\/s41467-024-49190-4","article-title":"Reservoir-computing based associative memory and itinerancy for complex dynamical attractors","volume":"15","author":"Kong","year":"2024","journal-title":"Nat. Commun."},{"key":"mlstaded56bib122","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.1.033056","article-title":"Model-free prediction of spatiotemporal dynamical systems with recurrent neural networks: role of network spectral radius","volume":"1","author":"Jiang","year":"2019","journal-title":"Phys. Rev. Res."},{"key":"mlstaded56bib123","doi-asserted-by":"publisher","DOI":"10.1063\/5.0082258","article-title":"A tighter generalization bound for reservoir computing","volume":"32","author":"Han","year":"2022","journal-title":"Chaos Interdiscip. J. Nonlinearr Sci."},{"key":"mlstaded56bib124","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1103\/PhysRevB.24.2613","article-title":"Random-energy model: an exactly solvable model of disordered systems","volume":"24","author":"Derrida","year":"1981","journal-title":"Phys. Rev. B"},{"key":"mlstaded56bib125","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1016\/0550-3213(84)90237-2","article-title":"The simplest spin glass","volume":"240","author":"Gross","year":"1984","journal-title":"Nucl. Phys. B"},{"key":"mlstaded56bib126","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1103\/PhysRevE.60.132","article-title":"Statistical mechanics of image restoration and error-correcting codes","volume":"60","author":"Nishimori","year":"1999","journal-title":"Phys. Rev. E"},{"year":"2001","author":"Nishimori","key":"mlstaded56bib127"},{"key":"mlstaded56bib128","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/s00440-005-0433-8","article-title":"Free energy of the spherical mean field model","volume":"134","author":"Talagrand","year":"2006","journal-title":"Probab. Theory Relat. Fields"},{"key":"mlstaded56bib129","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1214\/EJP.v18-2580","article-title":"The Aizenman-Sims-Starr scheme and Parisi formula for mixed p-spin spherical models","volume":"18","author":"Chen","year":"2013","journal-title":"Electron. J. Probab."},{"key":"mlstaded56bib130","doi-asserted-by":"publisher","first-page":"946","DOI":"10.1214\/12-AOP800","article-title":"The Parisi formula for mixed $p$-spin models","volume":"42","author":"Panchenko","year":"2014","journal-title":"Ann. Probab."},{"key":"mlstaded56bib131","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1007\/s00440-012-0460-1","article-title":"An approach to chaos in some mixed p-spin models","volume":"157","author":"Chen","year":"2013","journal-title":"Probab. Theory Relat. Fields"},{"key":"mlstaded56bib132","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.10.031045","article-title":"Rethinking mean-field glassy dynamics and its relation with the energy landscape: the surprising case of the spherical mixed p-spin model","volume":"10","author":"Folena","year":"2020","journal-title":"Phys. Rev. X"},{"key":"mlstaded56bib133","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8121\/acd66c","article-title":"Gauge theory for mixed p-spin glasses","volume":"56","author":"Itoi","year":"2023","journal-title":"J. Phys. Math. Theor."},{"key":"mlstaded56bib134","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ad7880","article-title":"Single-layer digitized-counterdiabatic quantum optimization for p-spin models","volume":"10","author":"Guan","year":"2024","journal-title":"Quantum Sci. Technol."},{"key":"mlstaded56bib135","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.5.040325","article-title":"Feedback-driven quantum reservoir computing for time-series analysis","volume":"5","author":"Kobayashi","year":"2024","journal-title":"PRX Quantum"},{"year":"2025","author":"Solanki","article-title":"Exploring tensor network algorithms as a quantum-inspired method for quantum reservoir computing","key":"mlstaded56bib136"},{"key":"mlstaded56bib137","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"mlstaded56bib138","doi-asserted-by":"publisher","DOI":"10.24432\/C50P49","article-title":"Optical recognition of handwritten digits","author":"Alpaydin","year":"1998"},{"key":"mlstaded56bib139","doi-asserted-by":"publisher","first-page":"0123","DOI":"10.34133\/icomputing.0123","article-title":"Compressing neural network by tensor network with exponentially fewer variational parameters","volume":"4","author":"Qing","year":"2025","journal-title":"Int. Comput."},{"key":"mlstaded56bib140","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/978-1-4612-1358-1_29","article-title":"Rademacher processes and bounding the risk of function learning","volume":"vol 47","author":"Koltchinskii","year":"2000"},{"key":"mlstaded56bib141","first-page":"463","article-title":"Rademacher and gaussian complexities: risk bounds and structural results","volume":"3","author":"Bartlett","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"mlstaded56bib142","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-018-5748-7","author":"Mohri","year":"2018","edition":"2nd edn"},{"year":"2020","author":"McInnes","article-title":"UMAP: uniform manifold approximation and projection for dimension reduction","key":"mlstaded56bib143"},{"key":"mlstaded56bib144","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1175\/1520-0469(1963)020<0130:DNF>2.0.CO;2","article-title":"Deterministic nonperiodic flow","volume":"20","author":"Lorenz","year":"1963","journal-title":"J. Atmos. Sci."},{"key":"mlstaded56bib145","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.1145\/3292500.3330701","article-title":"Optuna: a next-generation hyperparameter optimization framework","author":"Akiba","year":"2019"},{"year":"2015","author":"Sugiyama","key":"mlstaded56bib146"},{"key":"mlstaded56bib147","doi-asserted-by":"publisher","DOI":"10.3389\/fams.2021.716044","article-title":"Entanglement-based feature extraction by tensor network machine learning","volume":"7","author":"Liu","year":"2021","journal-title":"Front. Appl. Math. Stat."},{"key":"mlstaded56bib148","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.102.190501","article-title":"Most quantum states are too entangled to be useful as computational resources","volume":"102","author":"Gross","year":"2009","journal-title":"Phys. Rev. Lett."},{"year":"2022","author":"Aaronson","article-title":"How much structure is needed for huge quantum speedups?","key":"mlstaded56bib149"},{"key":"mlstaded56bib150","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.104.042408","article-title":"Tree-tensor-network classifiers for machine learning: from quantum inspired to quantum assisted","volume":"104","author":"Wall","year":"2021","journal-title":"Phys. Rev. A"},{"key":"mlstaded56bib151","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.122.160401","article-title":"Simulation complexity of open quantum dynamics: connection with tensor networks","volume":"122","author":"Luchnikov","year":"2019","journal-title":"Phys. Rev. Lett."},{"key":"mlstaded56bib152","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.105.104306","article-title":"Entanglement phase transitions in random stabilizer tensor networks","volume":"105","author":"Yang","year":"2022","journal-title":"Phys. Rev. B"},{"key":"mlstaded56bib153","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.13.021007","article-title":"Entanglement phase transition induced by the non-hermitian skin effect","volume":"13","author":"Kawabata","year":"2023","journal-title":"Phys. Rev. X"},{"key":"mlstaded56bib154","doi-asserted-by":"crossref","DOI":"10.1029\/2020MS002203","article-title":"WeatherBench: a benchmark dataset for data-driven weather forecasting","author":"Rasp","year":"2020"},{"author":"SILSO","article-title":"SIDC","key":"mlstaded56bib155"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded56","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded56\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded56","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded56\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded56\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded56\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded56\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded56\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T11:02:59Z","timestamp":1753182179000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aded56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,22]]},"references-count":155,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,7,22]]},"published-print":{"date-parts":[[2025,9,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/aded56","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,7,22]]},"assertion":[{"value":"Randomized tensor network reservoir computing: validity and learnability phase transitions","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-12-18","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-07-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-07-22","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}